379 terms

Automated Readability Index

The Automated Readability Index (ARI) is a readability test designed to gauge the understandability of a text by using a formula involving characters, words, and sentences.

Automatic Speech Recognition

Automatic Speech Recognition (ASR) is the technology that enables the conversion of spoken language into text by computers.

BabyAGI

BabyAGI is a simplified, experimental artificial general intelligence framework designed to explore the principles of AGI in a controlled environment.

Back-Translation

Back-Translation is the process of translating a document that has already been translated into another language back into the original language to ensure accuracy and consistency.

Bag of Words

Bag of Words is a text representation method used in natural language processing that models text as an unordered collection of words.

Bark

Bark is the outermost layer of stems and roots of woody plants, providing protection and aiding in nutrient transport.

Beam Search

Beam Search is a heuristic search algorithm that explores a graph by expanding the most promising nodes in a limited set, often used in natural language processing and machine translation.

Bi-Encoder

A Bi-Encoder is an AI model architecture used to generate embeddings for pairs of inputs, typically for tasks like retrieval or matching.

Bias Detection

Bias Detection is the process of identifying and addressing unfair preferences or prejudices in data, algorithms, or systems.

Bias Mitigation

Bias mitigation is the process of identifying, reducing, and managing unfair bias in AI systems, data, or decision-making processes.

Big-Bench

Big-Bench is a comprehensive benchmarking suite designed to evaluate the capabilities of large language models across a wide range of tasks.

BigBird

BigBird is a transformer-based natural language processing model designed to efficiently handle longer sequences of text.

Bigram

A bigram is a sequence of two adjacent elements from a string of tokens, which are typically letters, syllables, or words.

BlenderBot

BlenderBot is an advanced conversational AI model developed by Meta (formerly Facebook) to engage in dynamic and context-aware conversations with users.

BLEU Score

BLEU Score is a metric used to evaluate the quality of text generated by a machine translation system by comparing it to a reference translation.

BM25

BM25 is a ranking function used by search engines to score and rank documents based on their relevance to a given search query.

Boolean Search

Boolean Search is a technique that uses logical operators to refine and enhance search results.

Bronze Standard

Bronze Standard is a term used to describe a basic or minimum level of quality, service, or performance in a specific context.

ByT5

ByT5 is a multilingual text-to-text transformer model developed by Google for various natural language processing tasks.

Byte Pair Encoding

Byte Pair Encoding (BPE) is a data compression technique that replaces the most frequent pair of bytes in a dataset with a single, unused byte.

CANINE

A canine is a member of the family Canidae, which includes domestic dogs, wolves, foxes, and other related animals.

Causal Language Modeling

Causal Language Modeling is a type of language model that predicts the next word in a sequence based on the preceding text.

Cerebras

Cerebras is a tech company known for its development of advanced artificial intelligence computation hardware, particularly its wafer-scale engine (WSE) processors.

Chain-of-Thought Prompting

Chain-of-Thought Prompting is a technique in natural language processing where a model is guided to generate responses by mimicking a logical reasoning process.